Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4342 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.9281. Min Act: -0.0000

Data Index: 1929446 (The Pile)

Max Activating Token Index: 446

Text #1

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.8215. Min Act: -0.0000

Data Index: 550136 (The Pile)

Max Activating Token Index: 854

Text #2

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.7782. Min Act: -0.0000

Data Index: 386906 (The Pile)

Max Activating Token Index: 454

Text #3

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.7931. Min Act: -0.0000

Data Index: 1700935 (The Pile)

Max Activating Token Index: 592

Text #4

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.7760. Min Act: -0.0000

Data Index: 793203 (The Pile)

Max Activating Token Index: 120

Text #5

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.7704. Min Act: -0.0000

Data Index: 624565 (The Pile)

Max Activating Token Index: 926

Text #6

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.7614. Min Act: -0.0000

Data Index: 540396 (The Pile)

Max Activating Token Index: 903

Text #7

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.7691. Min Act: -0.0000

Data Index: 34519 (The Pile)

Max Activating Token Index: 778

Text #8

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.6310. Min Act: -0.0000

Data Index: 594966 (The Pile)

Max Activating Token Index: 975

Text #9

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.7111. Min Act: -0.0000

Data Index: 1093738 (The Pile)

Max Activating Token Index: 661

Text #10

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.7220. Min Act: -0.0000

Data Index: 1515283 (The Pile)

Max Activating Token Index: 539

Text #11

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.7194. Min Act: -0.0000

Data Index: 1560857 (The Pile)

Max Activating Token Index: 119

Text #12

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.7154. Min Act: -0.0000

Data Index: 1228124 (The Pile)

Max Activating Token Index: 928

Text #13

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.7242. Min Act: -0.0000

Data Index: 1213144 (The Pile)

Max Activating Token Index: 586

Text #14

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.6538. Min Act: -0.0000

Data Index: 1247245 (The Pile)

Max Activating Token Index: 463

Text #15

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.6943. Min Act: -0.0000

Data Index: 1010619 (The Pile)

Max Activating Token Index: 803

Text #16

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.6449. Min Act: -0.0000

Data Index: 1573006 (The Pile)

Max Activating Token Index: 483

Text #17

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.6629. Min Act: -0.0000

Data Index: 131657 (The Pile)

Max Activating Token Index: 663

Text #18

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.6396. Min Act: -0.0000

Data Index: 17492 (The Pile)

Max Activating Token Index: 969

Text #19

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.6541. Min Act: -0.0000

Data Index: 1688416 (The Pile)

Max Activating Token Index: 670